1CALLGRIND CONTROL(1) Release 3.5.0 CALLGRIND CONTROL(1)
2
3
4
6 callgrind_control - observe and control programs being run by Callgrind
7
9 callgrind_control [options] [pid|program-name...]
10
12 callgrind_control controls programs being run by the Valgrind tool
13 Callgrind. When a pid/program name argument is not specified, all
14 applications currently being run by Callgrind on this system will be
15 used for actions given by the specified option(s). The default action
16 is to give some brief information about the applications being run by
17 Callgrind.
18
20 -h --help
21 Show a short description, usage, and summary of options.
22
23 --version
24 Show version of callgrind_control.
25
26 -l --long
27 Show also the working directory, in addition to the brief
28 information given by default.
29
30 -s --stat
31 Show statistics information about active Callgrind runs.
32
33 -b --back
34 Show stack/back traces of each thread in active Callgrind runs.
35 For each active function in the stack trace, also the number of
36 invocations since program start (or last dump) is shown. This
37 option can be combined with -e to show inclusive cost of active
38 functions.
39
40 -e [A,B,...] (default: all)
41 Show the current per-thread, exclusive cost values of event
42 counters. If no explicit event names are given, figures for all
43 event types which are collected in the given Callgrind run are
44 shown. Otherwise, only figures for event types A, B, ... are
45 shown. If this option is combined with -b, inclusive cost for
46 the functions of each active stack frame is provided, too.
47
48 --dump[=<desc>] (default: no description)
49 Request the dumping of profile information. Optionally, a
50 description can be specified which is written into the dump as
51 part of the information giving the reason which triggered the
52 dump action. This can be used to distinguish multiple dumps.
53
54 -z --zero
55 Zero all event counters.
56
57 -k --kill
58 Force a Callgrind run to be terminated.
59
60 --instr=<on|off>
61 Switch instrumentation mode on or off. If a Callgrind run has
62 instrumentation disabled, no simulation is done and no events
63 are counted. This is useful to skip uninteresting program parts,
64 as there is much less slowdown (same as with the Valgrind tool
65 "none"). See also the Callgrind option --instr-atstart.
66
67 -w=<dir>
68 Specify the startup directory of an active Callgrind run. On
69 some systems, active Callgrind runs can not be detected. To be
70 able to control these, the failed auto-detection can be worked
71 around by specifying the directory where a Callgrind run was
72 started.
73
75 valgrind(1), $INSTALL/share/doc/valgrind/html/index.html or
76 http://www.valgrind.org/docs/manual/index.html.
77
79 Josef Weidendorfer <Josef.Weidendorfer@gmx.de>.
80
81
82
83Release 3.5.0 08/19/2009 CALLGRIND CONTROL(1)